Mechanism of Parked Domains Recognition Based on Authoritative DNS Servers

At present, there are a large number of parked domains, which seriously affect online users when surfing. To identify parked domains effectively, a new technique was proposed based on authoritative Domain Name Server (DNS). In this way, suspected authoritative DNS servers of typosquatting domains were extracted, which commonly used in domain parking service. Then these DNS servers were clustered by semi-supervised clustering method, to identify whether they were associated with domain parking service. When detecting a parked domain, we can identify it by judging whether its authoritative DNS applied in domain parking service and whether its mapping IP addresses concluded in the set od IP addresses of parking web servers. With existing detecting method by using webpage's features to analyze the accuracy of the proposed method, the experimental results show the proposed method achieves a high accuracy rate of 92.8%, avoids crawling the webpages, has a good performance on parked domains detection in real time.

[1]  Wouter Joosen,et al.  Bitsquatting: exploiting bit-flips for fun, or profit? , 2013, WWW '13.

[2]  Wouter Joosen,et al.  Soundsquatting: Uncovering the Use of Homophones in Domain Squatting , 2014, ISC.

[3]  Anthony McGregor,et al.  Flow Clustering Using Machine Learning Techniques , 2004, PAM.

[4]  Stefan Savage,et al.  XXXtortion?: inferring registration intent in the .XXX TLD , 2014, WWW.

[5]  Vern Paxson,et al.  The BIZ Top-Level Domain: Ten Years Later , 2012, PAM.

[6]  Zhou Li,et al.  Understanding the Dark Side of Domain Parking , 2014, USENIX Security Symposium.

[7]  Carey L. Williamson,et al.  Offline/realtime traffic classification using semi-supervised learning , 2007, Perform. Evaluation.

[8]  Padhraic Smyth,et al.  Model selection for probabilistic clustering using cross-validated likelihood , 2000, Stat. Comput..

[9]  Ian H. Witten,et al.  Data Mining: Practical Machine Learning Tools and Techniques, 3/E , 2014 .

[10]  Heng Du.  Domain Parking Recognizer: an experimental study on web content categorization , 2013 .

[11]  Wouter Joosen,et al.  Seven Months' Worth of Mistakes: A Longitudinal Study of Typosquatting Abuse , 2015, NDSS.

[12]  Wouter Joosen,et al.  Parking Sensors: Analyzing and Detecting Parked Domains , 2015, NDSS.

[13]  Chris Kanich,et al.  The Long "Taile" of Typosquatting Domain Names , 2014, USENIX Security Symposium.

[14]  Tyler Moore,et al.  Measuring the Perpetrators and Funders of Typosquatting , 2010, Financial Cryptography.